In recent years, Artificial Intelligence (AI) provided essential tools to enhance the productivity of activities related to civil engineering, particularly in design, construction, and maintenance. In this framework, the present work proposes a novel AI computer vision methodology for automatically identifying the corrosion phenomenon on roofing systems of large-scale industrial buildings. The proposed method can be incorporated into computational packages for easier integration by the industry to enhance the inspection activities’ performance. For this purpose, a dedicated image database with more than 8k high-resolution aerial images was developed for supervised training. An Unmanned Aerial Vehicle (UAV) was used to acquire remote georeferenced images safely and efficiently. The corrosion anomalies were manually annotated using a segmentation strategy summing up 18,381 instances. These anomalies were identified through instance segmentation using the Mask based Region-Convolution Neural Network (Mask R-CNN) framework adjusted to the created dataset. Some adjustments were performed to enhance the performance of the classification model, particularly defining an adequate input image size, data augmentation strategy, Intersection over a Union (IoU) threshold during training, and type of backbone network. The inferences show promising results, with correct detections even under complex backgrounds, poor illumination conditions, and instances of significantly reduced dimensions. Furthermore, in scenarios without a roofing system, the model proved reliable, not producing any false positive occurrences. The best model achieved metrics’ values equal to 65.1% for the bounding box detection Average Precision (AP) and 59.2% for the mask AP, considering an IoU of 50%. Regarding classification metrics, the precision and recall were equal to 85.8% and 84.0%, respectively. The developed methodology proved to be extremely valuable for guiding infrastructure managers in taking physically informed decisions based on the real assets condition.

Documentation of structural visual inspections is necessary for its monitoring, maintenance, and decision about its rehabilitation, and structural strengthening. In recent times, close-range photogrammetry (CRP) based on unmanned aerial vehicles (UAVs) and terrestrial laser scanners (TLS) have greatly improved the survey phase. These technologies can be used independently or in combination to provide a 3D as-is image-based model of the railway bridge. In this study, TLS captured the side and bottom sections of the deck, while the CRP-based UAV captured the side and top sections of the deck, and the track. The combination of post-processing techniques enabled the merging of TLS and CRP models, resulting in the creation of an accurate 3D representation of the complete railway bridge deck. Additionally, a 3D as-designed model was developed based on the design plans of the bridge. The as-designed model is compared to the as-is model through a 3D digital registration. The comparison allows the detection of dimensional deviation and surface alignments. The results reveal slight deviations in the structural dimension with a global average value of 9 mm.

This article addresses the state of the art of methodologies for bridge inspection with potential for inclusion in Bridge Management Systems (BMS) and within the scope of the IABSE Task Group 5.9 on Remote Inspection of Bridges. The document covers computer vision approaches, including 3D geometric reconstitution (photogrammetry, LiDAR, and hybrid fusion strategies), damage and component identification (based on heuristics and Artificial Intelligence), and non-contact measurement of key structural parameters (displacements, strains, and modal parameters). Additionally, it addresses techniques for handling the large volumes of data generated by bridge inspections (Big Data), the use of Digital Twins for asset maintenance, and dedicated applications of Augmented Reality based on immersive environments for bridge inspection. These methodologies will contribute to safe, automated, and intelligent assessment and maintenance of bridges, enhancing resilience and lifespan of transportation infrastructure under changing climate.

The automated inspection of civil infrastructure with Unmanned Aerial Vehicles (UAVs) is hampered by the challenge of accurately segmenting multi-damage in high-resolution imagery. While foundational models like the Segment Anything Model (SAM) offer data-efficient segmentation, their effectiveness is constrained by prompting strategies, especially for geometrically complex defects. This paper presents a comprehensive comparative analysis of deep learning strategies to identify an optimal deep learning pipeline for segmenting cracks, efflorescences, and exposed rebars. It systematically evaluates three distinct end-to-end segmentation frameworks: the native output of a YOLO11 model; the Segment Anything Model (SAM), prompted by bounding boxes; and SAM, guided by a point-prompting mechanism derived from the detector’s probability map. Based on these findings, a final, optimized hybrid pipeline is proposed: for linear cracks, the native segmentation output of the SAHI-trained YOLO model is used, while for efflorescence and exposed rebar, the model’s bounding boxes are used to prompt SAM for a refined segmentation. This class-specific strategy yielded a final mean Average Precision (mAP50) of 0.593, with class-specific Intersection over Union (IoU) scores of 0.495 (cracks), 0.331 (efflorescence), and 0.205 (exposed rebar). The results establish that the future of automated inspection lies in intelligent frameworks that leverage the respective strengths of specialized detectors and powerful foundation models in a context-aware manner.